The first property you should note is that the proportion of ones in a binary distribution is equal to the mean of the distribution. Think about why this is true. Complete the following cell to show that this is the case for your binary_sample. Assign number of ones and number_of_zeros to the number of i 's and the number of O's respectively from your binary_sample. number_of_ones = ...
number of zeros = ...
# DON'T DELETE/MODIFY ANY OF THE CODE BELOW IN THIS CELL
number_values = len (binary_sample)
sum of binary_sample = sum(binary_sample)
# Remember that the mean is equal to the sum divided by the number of items
mean_binary_sample = sum_of_binary_sample / number_values
# Don't change this!
print(f"In your binary sample there were {number_of_ones} ones and {number_of_zeros} zero
print(f"The sum of values in your sample was {sum_of_binary_sample}, divided by the numbe
print(f"The proportion of ones in your sample was {number_of_ones} ones, divided by the n
print('Those values are equal!')
ok. grade("q2_2");
Since the proportion of ones is the same as the mean, the Central Limit Theorem applies! That is, if we resample our sample a lot of times, the distribution of the proportion of ones in our resamples will be roughly normal, with a predictable center and spread!
# Just run this cell resampled_proportion_of_ones = make_array()
for i in np. arange (5000):
resample = Table().with_column("Value", binary_sample).sample()
resample_proportion_ones = resample. where("Value", 1).num_rows /
resample. num_rows resampled_proportion_of_ones = np. append(resampled_proportion_of_ones , resample_propo:
Table().with_column('Resampled Proportions', resampled_proportion_of_ones).hist( )
Let's generate a table where each row has a different number of ones and zeros that we'll use for the following parts. # Just run this cell possible_number_ones = np. arange (sample_size + 1) possible number zeros = sample size - possible number ones possibilities_table = Table().with_columns ("Values of One", possible_number_ones, "Values possibilities_table. Show (5)